Merge pull request 'feat(learning): מסלול נקי להעלאת החלטה סופית + פאנל-סגנון דו-סוכני (DeepSeek+Gemini)' (#158) from worktree-final-upload-pipeline into main

web/app.py

@@ -3312,6 +3312,128 @@ async def api_mark_final(case_number: str, filename: str):
     }
 
 
+@app.post("/api/cases/{case_number}/final/upload")
+async def api_upload_final_decision(case_number: str, file: UploadFile = File(...)):
+    """Clean path: upload the CHAIR's signed final decision (Dafna's version).
+
+    Distinct from the two pre-existing flows:
+      • exports/upload  → uploads a *revised version of OUR draft* (retrofits bookmarks,
+        becomes active_draft). NOT for the chair's final.
+      • exports/{f}/mark-final → marks one of *our* exports as final.
+
+    This endpoint takes the EXTERNAL signed final, stores it canonically, enrolls it in
+    the style corpus, and opens the draft↔final reconciliation pair (INV-LRN4) so the
+    staged learning step can persist its analysis. It does NOT touch active_draft and
+    does NOT run the LLM pipeline (run-learning / run-halacha do, on the local worker).
+    """
+    case = await db.get_case_by_number(case_number)
+    if not case:
+        raise HTTPException(404, f"תיק {case_number} לא נמצא")
+    if not file.filename:
+        raise HTTPException(400, "לא צוין שם קובץ")
+    if Path(file.filename).suffix.lower() != ".docx":
+        raise HTTPException(400, "רק קבצי DOCX נתמכים")
+    content = await file.read()
+    if len(content) > MAX_FILE_SIZE:
+        raise HTTPException(400, f"קובץ גדול מדי. מקסימום: {MAX_FILE_SIZE // (1024*1024)}MB")
+
+    export_dir = config.find_case_dir(case_number) / "exports"
+    export_dir.mkdir(parents=True, exist_ok=True)
+    final_name = f"סופי-{case_number}.docx"
+    final_path = export_dir / final_name
+    final_path.write_bytes(content)
+
+    # Enroll in the style corpus. Use the FULL case_number as decision_number so a
+    # בל"מ never collides with a same-numbered ערר already in the corpus (e.g. ARAR-25-8126).
+    config.TRAINING_DIR.mkdir(parents=True, exist_ok=True)
+    training_dest = config.TRAINING_DIR / f"החלטה-{case_number}.docx"
+    shutil.copy2(str(final_path), str(training_dest))
+
+    # Extract the final text (word count for the UI; full text snapshotted into the pair).
+    final_text = ""
+    try:
+        final_text, _pages, _ = await extractor.extract_text(str(final_path))
+    except Exception as e:
+        logger.warning("final text extraction failed for %s: %s", case_number, e)
+
+    # Case → final.
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        await conn.execute(
+            "UPDATE cases SET status = 'final', updated_at = now() WHERE id = $1",
+            UUID(case["id"]),
+        )
+
+    # INV-LRN4 — snapshot OUR draft now and open the pair (status=final_received).
+    pair_id: str | None = None
+    draft_words = 0
+    try:
+        decision = await db.get_decision_by_case(UUID(case["id"]))
+        draft_text = ""
+        if decision:
+            async with pool.acquire() as conn:
+                brows = await conn.fetch(
+                    "SELECT content FROM decision_blocks "
+                    "WHERE decision_id = $1 AND word_count > 0 ORDER BY block_index",
+                    UUID(decision["id"]),
+                )
+            draft_text = "\n\n".join(b["content"] for b in brows if b["content"])
+        draft_words = len(draft_text.split())
+        pair_id = await db.create_draft_final_pair(
+            UUID(case["id"]), draft_text, str(final_path),
+        )
+    except Exception as e:
+        logger.warning("draft_final_pair snapshot failed for %s: %s", case_number, e)
+
+    case_dir = config.find_case_dir(case_number)
+    if case_dir.exists():
+        commit_and_push(case_dir, f"החלטה סופית של היו\"ר: {final_name}")
+
+    return {
+        "final_filename": final_name,
+        "training_copy": str(training_dest),
+        "pair_id": pair_id,
+        "draft_words": draft_words,
+        "final_words": len(final_text.split()),
+        "status": "final",
+    }
+
+
+async def _wake_final_task(case_number: str, task: str) -> dict:
+    """Shared trigger for the staged learning / halacha steps — wakes the local curator."""
+    case = await db.get_case_by_number(case_number)
+    if not case:
+        raise HTTPException(404, f"תיק {case_number} לא נמצא")
+    final_name = f"סופי-{case_number}.docx"
+    prefix = case_number[:1]
+    company_id = (
+        PAPERCLIP_COMPANIES["licensing"] if prefix == "1"
+        else PAPERCLIP_COMPANIES["betterment"] if prefix in ("8", "9")
+        else ""
+    )
+    try:
+        return await pc_wake_curator_for_final(
+            case_number, final_name, company_id=company_id, task=task,
+        )
+    except Exception as e:
+        logger.warning("final %s wakeup failed for %s: %s", task, case_number, e)
+        return {"status": "error", "error": str(e)}
+
+
+@app.post("/api/cases/{case_number}/final/run-learning")
+async def api_final_run_learning(case_number: str):
+    """Staged step 1 — voice learning: wake the local worker to run ingest_final_version
+    (Opus distillation) + the 2-judge style panel (DeepSeek+Gemini)."""
+    return await _wake_final_task(case_number, "learning")
+
+
+@app.post("/api/cases/{case_number}/final/run-halacha")
+async def api_final_run_halacha(case_number: str):
+    """Staged step 2 — halacha validation: wake the local worker to extract the cited
+    halachot, build corroboration, and run the 3-judge halacha panel (--apply)."""
+    return await _wake_final_task(case_number, "halacha")
+
+
 @app.post("/api/cases/{case_number}/export-docx")
 async def api_export_docx(case_number: str, background_tasks: BackgroundTasks):
     """Trigger DOCX export for a case.